Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent
This work addresses the need for explainable AI in causal modeling, though it is incremental as it adapts existing autoencoder concepts to FCMs with an LLM.
The paper tackles the problem of generating interpretable text representations of feedback fuzzy cognitive maps (FCMs) using a large language model (LLM) agent, resulting in a lossy reconstruction that preserves strong causal edges while removing weak ones.
A large language model (LLM) can map a feedback causal fuzzy cognitive map (FCM) into text and then reconstruct the FCM from the text. This explainable AI system approximates an identity map from the FCM to itself and resembles the operation of an autoencoder (AE). Both the encoder and the decoder explain their decisions in contrast to black-box AEs. Humans can read and interpret the encoded text in contrast to the hidden variables and synaptic webs in AEs. The LLM agent approximates the identity map through a sequence of system instructions that does not compare the output to the input. The reconstruction is lossy because it removes weak causal edges or rules while it preserves strong causal edges. The encoder preserves the strong causal edges even when it trades off some details about the FCM to make the text sound more natural.